target_ulong helper_read_crN(CPUX86State *env, int reg)
{
target_ulong val;
cpu_svm_check_intercept_param(env, SVM_EXIT_READ_CR0 + reg, 0, GETPC());
switch (reg) {
default:
val = env->cr[reg];
break;
case 8:
if (!(env->hflags2 & HF2_VINTR_MASK)) {
val = cpu_get_apic_tpr(x86_env_get_cpu(env)->apic_state);
} else {
val = env->v_tpr;
}
break;
}
return val;
}
static void whpx_set_registers(CPUState *cpu)
{
struct whpx_state *whpx = &whpx_global;
struct whpx_vcpu *vcpu = get_whpx_vcpu(cpu);
struct CPUX86State *env = (CPUArchState *)(cpu->env_ptr);
X86CPU *x86_cpu = X86_CPU(cpu);
struct whpx_register_set vcxt = {0};
HRESULT hr;
int idx = 0;
int i;
int v86, r86;
assert(cpu_is_stopped(cpu) || qemu_cpu_is_self(cpu));
v86 = (env->eflags & VM_MASK);
r86 = !(env->cr[0] & CR0_PE_MASK);
vcpu->tpr = cpu_get_apic_tpr(x86_cpu->apic_state);
vcpu->apic_base = cpu_get_apic_base(x86_cpu->apic_state);
/* Indexes for first 16 registers match between HV and QEMU definitions */
for (idx = 0; idx < CPU_NB_REGS64; idx += 1) {
vcxt.values[idx].Reg64 = env->regs[idx];
}
/* Same goes for RIP and RFLAGS */
assert(whpx_register_names[idx] == WHvX64RegisterRip);
vcxt.values[idx++].Reg64 = env->eip;
assert(whpx_register_names[idx] == WHvX64RegisterRflags);
vcxt.values[idx++].Reg64 = env->eflags;
/* Translate 6+4 segment registers. HV and QEMU order matches */
assert(idx == WHvX64RegisterEs);
for (i = 0; i < 6; i += 1, idx += 1) {
vcxt.values[idx].Segment = whpx_seg_q2h(&env->segs[i], v86, r86);
}
assert(idx == WHvX64RegisterLdtr);
vcxt.values[idx++].Segment = whpx_seg_q2h(&env->ldt, 0, 0);
assert(idx == WHvX64RegisterTr);
vcxt.values[idx++].Segment = whpx_seg_q2h(&env->tr, 0, 0);
assert(idx == WHvX64RegisterIdtr);
vcxt.values[idx].Table.Base = env->idt.base;
vcxt.values[idx].Table.Limit = env->idt.limit;
idx += 1;
assert(idx == WHvX64RegisterGdtr);
vcxt.values[idx].Table.Base = env->gdt.base;
vcxt.values[idx].Table.Limit = env->gdt.limit;
idx += 1;
/* CR0, 2, 3, 4, 8 */
assert(whpx_register_names[idx] == WHvX64RegisterCr0);
vcxt.values[idx++].Reg64 = env->cr[0];
assert(whpx_register_names[idx] == WHvX64RegisterCr2);
vcxt.values[idx++].Reg64 = env->cr[2];
assert(whpx_register_names[idx] == WHvX64RegisterCr3);
vcxt.values[idx++].Reg64 = env->cr[3];
assert(whpx_register_names[idx] == WHvX64RegisterCr4);
vcxt.values[idx++].Reg64 = env->cr[4];
assert(whpx_register_names[idx] == WHvX64RegisterCr8);
vcxt.values[idx++].Reg64 = vcpu->tpr;
/* 8 Debug Registers - Skipped */
/* 16 XMM registers */
assert(whpx_register_names[idx] == WHvX64RegisterXmm0);
for (i = 0; i < 16; i += 1, idx += 1) {
vcxt.values[idx].Reg128.Low64 = env->xmm_regs[i].ZMM_Q(0);
vcxt.values[idx].Reg128.High64 = env->xmm_regs[i].ZMM_Q(1);
}
/* 8 FP registers */
assert(whpx_register_names[idx] == WHvX64RegisterFpMmx0);
for (i = 0; i < 8; i += 1, idx += 1) {
vcxt.values[idx].Fp.AsUINT128.Low64 = env->fpregs[i].mmx.MMX_Q(0);
/* vcxt.values[idx].Fp.AsUINT128.High64 =
env->fpregs[i].mmx.MMX_Q(1);
*/
}
/* FP control status register */
assert(whpx_register_names[idx] == WHvX64RegisterFpControlStatus);
vcxt.values[idx].FpControlStatus.FpControl = env->fpuc;
vcxt.values[idx].FpControlStatus.FpStatus =
(env->fpus & ~0x3800) | (env->fpstt & 0x7) << 11;
vcxt.values[idx].FpControlStatus.FpTag = 0;
for (i = 0; i < 8; ++i) {
vcxt.values[idx].FpControlStatus.FpTag |= (!env->fptags[i]) << i;
}
vcxt.values[idx].FpControlStatus.Reserved = 0;
vcxt.values[idx].FpControlStatus.LastFpOp = env->fpop;
vcxt.values[idx].FpControlStatus.LastFpRip = env->fpip;
idx += 1;
/* XMM control status register */
assert(whpx_register_names[idx] == WHvX64RegisterXmmControlStatus);
vcxt.values[idx].XmmControlStatus.LastFpRdp = 0;
vcxt.values[idx].XmmControlStatus.XmmStatusControl = env->mxcsr;
vcxt.values[idx].XmmControlStatus.XmmStatusControlMask = 0x0000ffff;
idx += 1;
/* MSRs */
assert(whpx_register_names[idx] == WHvX64RegisterTsc);
vcxt.values[idx++].Reg64 = env->tsc;
assert(whpx_register_names[idx] == WHvX64RegisterEfer);
vcxt.values[idx++].Reg64 = env->efer;
#ifdef TARGET_X86_64
assert(whpx_register_names[idx] == WHvX64RegisterKernelGsBase);
vcxt.values[idx++].Reg64 = env->kernelgsbase;
#endif
assert(whpx_register_names[idx] == WHvX64RegisterApicBase);
vcxt.values[idx++].Reg64 = vcpu->apic_base;
/* WHvX64RegisterPat - Skipped */
assert(whpx_register_names[idx] == WHvX64RegisterSysenterCs);
vcxt.values[idx++].Reg64 = env->sysenter_cs;
assert(whpx_register_names[idx] == WHvX64RegisterSysenterEip);
vcxt.values[idx++].Reg64 = env->sysenter_eip;
assert(whpx_register_names[idx] == WHvX64RegisterSysenterEsp);
vcxt.values[idx++].Reg64 = env->sysenter_esp;
assert(whpx_register_names[idx] == WHvX64RegisterStar);
vcxt.values[idx++].Reg64 = env->star;
#ifdef TARGET_X86_64
assert(whpx_register_names[idx] == WHvX64RegisterLstar);
vcxt.values[idx++].Reg64 = env->lstar;
assert(whpx_register_names[idx] == WHvX64RegisterCstar);
vcxt.values[idx++].Reg64 = env->cstar;
assert(whpx_register_names[idx] == WHvX64RegisterSfmask);
vcxt.values[idx++].Reg64 = env->fmask;
#endif
/* Interrupt / Event Registers - Skipped */
assert(idx == RTL_NUMBER_OF(whpx_register_names));
hr = WHvSetVirtualProcessorRegisters(whpx->partition, cpu->cpu_index,
whpx_register_names,
RTL_NUMBER_OF(whpx_register_names),
&vcxt.values[0]);
if (FAILED(hr)) {
error_report("WHPX: Failed to set virtual processor context, hr=%08lx",
hr);
}
return;
}
static void whpx_vcpu_pre_run(CPUState *cpu)
{
HRESULT hr;
struct whpx_state *whpx = &whpx_global;
struct whpx_vcpu *vcpu = get_whpx_vcpu(cpu);
struct CPUX86State *env = (CPUArchState *)(cpu->env_ptr);
X86CPU *x86_cpu = X86_CPU(cpu);
int irq;
uint8_t tpr;
WHV_X64_PENDING_INTERRUPTION_REGISTER new_int = {0};
UINT32 reg_count = 0;
WHV_REGISTER_VALUE reg_values[3] = {0};
WHV_REGISTER_NAME reg_names[3];
qemu_mutex_lock_iothread();
/* Inject NMI */
if (!vcpu->interrupt_in_flight.InterruptionPending &&
cpu->interrupt_request & (CPU_INTERRUPT_NMI | CPU_INTERRUPT_SMI)) {
if (cpu->interrupt_request & CPU_INTERRUPT_NMI) {
cpu->interrupt_request &= ~CPU_INTERRUPT_NMI;
vcpu->interruptable = false;
new_int.InterruptionType = WHvX64PendingNmi;
new_int.InterruptionPending = 1;
new_int.InterruptionVector = 2;
}
if (cpu->interrupt_request & CPU_INTERRUPT_SMI) {
cpu->interrupt_request &= ~CPU_INTERRUPT_SMI;
}
}
/*
* Force the VCPU out of its inner loop to process any INIT requests or
* commit pending TPR access.
*/
if (cpu->interrupt_request & (CPU_INTERRUPT_INIT | CPU_INTERRUPT_TPR)) {
if ((cpu->interrupt_request & CPU_INTERRUPT_INIT) &&
!(env->hflags & HF_SMM_MASK)) {
cpu->exit_request = 1;
}
if (cpu->interrupt_request & CPU_INTERRUPT_TPR) {
cpu->exit_request = 1;
}
}
/* Get pending hard interruption or replay one that was overwritten */
if (!vcpu->interrupt_in_flight.InterruptionPending &&
vcpu->interruptable && (env->eflags & IF_MASK)) {
assert(!new_int.InterruptionPending);
if (cpu->interrupt_request & CPU_INTERRUPT_HARD) {
cpu->interrupt_request &= ~CPU_INTERRUPT_HARD;
irq = cpu_get_pic_interrupt(env);
if (irq >= 0) {
new_int.InterruptionType = WHvX64PendingInterrupt;
new_int.InterruptionPending = 1;
new_int.InterruptionVector = irq;
}
}
}
/* Setup interrupt state if new one was prepared */
if (new_int.InterruptionPending) {
reg_values[reg_count].PendingInterruption = new_int;
reg_names[reg_count] = WHvRegisterPendingInterruption;
reg_count += 1;
}
/* Sync the TPR to the CR8 if was modified during the intercept */
tpr = cpu_get_apic_tpr(x86_cpu->apic_state);
if (tpr != vcpu->tpr) {
vcpu->tpr = tpr;
reg_values[reg_count].Reg64 = tpr;
cpu->exit_request = 1;
reg_names[reg_count] = WHvX64RegisterCr8;
reg_count += 1;
}
/* Update the state of the interrupt delivery notification */
if (!vcpu->window_registered &&
cpu->interrupt_request & CPU_INTERRUPT_HARD) {
reg_values[reg_count].DeliverabilityNotifications.InterruptNotification
= 1;
vcpu->window_registered = 1;
reg_names[reg_count] = WHvX64RegisterDeliverabilityNotifications;
reg_count += 1;
}
qemu_mutex_unlock_iothread();
if (reg_count) {
hr = WHvSetVirtualProcessorRegisters(whpx->partition, cpu->cpu_index,
reg_names, reg_count, reg_values);
if (FAILED(hr)) {
error_report("WHPX: Failed to set interrupt state registers,"
" hr=%08lx", hr);
}
}
return;
}
void kvm_arch_load_regs(CPUState *env, int level)
{
struct kvm_regs regs;
struct kvm_fpu fpu;
struct kvm_sregs sregs;
struct kvm_msr_entry msrs[100];
int rc, n, i;
assert(kvm_cpu_is_stopped(env) || env->thread_id == kvm_get_thread_id());
regs.rax = env->regs[R_EAX];
regs.rbx = env->regs[R_EBX];
regs.rcx = env->regs[R_ECX];
regs.rdx = env->regs[R_EDX];
regs.rsi = env->regs[R_ESI];
regs.rdi = env->regs[R_EDI];
regs.rsp = env->regs[R_ESP];
regs.rbp = env->regs[R_EBP];
#ifdef TARGET_X86_64
regs.r8 = env->regs[8];
regs.r9 = env->regs[9];
regs.r10 = env->regs[10];
regs.r11 = env->regs[11];
regs.r12 = env->regs[12];
regs.r13 = env->regs[13];
regs.r14 = env->regs[14];
regs.r15 = env->regs[15];
#endif
regs.rflags = env->eflags;
regs.rip = env->eip;
kvm_set_regs(env, ®s);
#ifdef KVM_CAP_XSAVE
if (kvm_check_extension(kvm_state, KVM_CAP_XSAVE)) {
struct kvm_xsave* xsave;
uint16_t cwd, swd, twd, fop;
xsave = qemu_memalign(4096, sizeof(struct kvm_xsave));
memset(xsave, 0, sizeof(struct kvm_xsave));
cwd = swd = twd = fop = 0;
swd = env->fpus & ~(7 << 11);
swd |= (env->fpstt & 7) << 11;
cwd = env->fpuc;
for (i = 0; i < 8; ++i)
twd |= (!env->fptags[i]) << i;
xsave->region[0] = (uint32_t)(swd << 16) + cwd;
xsave->region[1] = (uint32_t)(fop << 16) + twd;
memcpy(&xsave->region[XSAVE_ST_SPACE], env->fpregs,
sizeof env->fpregs);
memcpy(&xsave->region[XSAVE_XMM_SPACE], env->xmm_regs,
sizeof env->xmm_regs);
xsave->region[XSAVE_MXCSR] = env->mxcsr;
*(uint64_t *)&xsave->region[XSAVE_XSTATE_BV] = env->xstate_bv;
memcpy(&xsave->region[XSAVE_YMMH_SPACE], env->ymmh_regs,
sizeof env->ymmh_regs);
kvm_set_xsave(env, xsave);
if (kvm_check_extension(kvm_state, KVM_CAP_XCRS)) {
struct kvm_xcrs xcrs;
xcrs.nr_xcrs = 1;
xcrs.flags = 0;
xcrs.xcrs[0].xcr = 0;
xcrs.xcrs[0].value = env->xcr0;
kvm_set_xcrs(env, &xcrs);
}
qemu_free(xsave);
} else {
#endif
memset(&fpu, 0, sizeof fpu);
fpu.fsw = env->fpus & ~(7 << 11);
fpu.fsw |= (env->fpstt & 7) << 11;
fpu.fcw = env->fpuc;
for (i = 0; i < 8; ++i)
fpu.ftwx |= (!env->fptags[i]) << i;
memcpy(fpu.fpr, env->fpregs, sizeof env->fpregs);
memcpy(fpu.xmm, env->xmm_regs, sizeof env->xmm_regs);
fpu.mxcsr = env->mxcsr;
kvm_set_fpu(env, &fpu);
#ifdef KVM_CAP_XSAVE
}
#endif
memset(sregs.interrupt_bitmap, 0, sizeof(sregs.interrupt_bitmap));
if (env->interrupt_injected >= 0) {
sregs.interrupt_bitmap[env->interrupt_injected / 64] |=
(uint64_t)1 << (env->interrupt_injected % 64);
}
if ((env->eflags & VM_MASK)) {
set_v8086_seg(&sregs.cs, &env->segs[R_CS]);
set_v8086_seg(&sregs.ds, &env->segs[R_DS]);
set_v8086_seg(&sregs.es, &env->segs[R_ES]);
set_v8086_seg(&sregs.fs, &env->segs[R_FS]);
set_v8086_seg(&sregs.gs, &env->segs[R_GS]);
set_v8086_seg(&sregs.ss, &env->segs[R_SS]);
} else {
set_seg(&sregs.cs, &env->segs[R_CS]);
set_seg(&sregs.ds, &env->segs[R_DS]);
set_seg(&sregs.es, &env->segs[R_ES]);
set_seg(&sregs.fs, &env->segs[R_FS]);
set_seg(&sregs.gs, &env->segs[R_GS]);
set_seg(&sregs.ss, &env->segs[R_SS]);
if (env->cr[0] & CR0_PE_MASK) {
/* force ss cpl to cs cpl */
sregs.ss.selector = (sregs.ss.selector & ~3) |
(sregs.cs.selector & 3);
sregs.ss.dpl = sregs.ss.selector & 3;
}
}
set_seg(&sregs.tr, &env->tr);
set_seg(&sregs.ldt, &env->ldt);
sregs.idt.limit = env->idt.limit;
sregs.idt.base = env->idt.base;
sregs.gdt.limit = env->gdt.limit;
sregs.gdt.base = env->gdt.base;
sregs.cr0 = env->cr[0];
sregs.cr2 = env->cr[2];
sregs.cr3 = env->cr[3];
sregs.cr4 = env->cr[4];
sregs.cr8 = cpu_get_apic_tpr(env->apic_state);
sregs.apic_base = cpu_get_apic_base(env->apic_state);
sregs.efer = env->efer;
kvm_set_sregs(env, &sregs);
/* msrs */
n = 0;
/* Remember to increase msrs size if you add new registers below */
kvm_msr_entry_set(&msrs[n++], MSR_IA32_SYSENTER_CS, env->sysenter_cs);
kvm_msr_entry_set(&msrs[n++], MSR_IA32_SYSENTER_ESP, env->sysenter_esp);
kvm_msr_entry_set(&msrs[n++], MSR_IA32_SYSENTER_EIP, env->sysenter_eip);
if (kvm_has_msr_star)
kvm_msr_entry_set(&msrs[n++], MSR_STAR, env->star);
if (kvm_has_vm_hsave_pa)
kvm_msr_entry_set(&msrs[n++], MSR_VM_HSAVE_PA, env->vm_hsave);
#ifdef TARGET_X86_64
if (lm_capable_kernel) {
kvm_msr_entry_set(&msrs[n++], MSR_CSTAR, env->cstar);
kvm_msr_entry_set(&msrs[n++], MSR_KERNELGSBASE, env->kernelgsbase);
kvm_msr_entry_set(&msrs[n++], MSR_FMASK, env->fmask);
kvm_msr_entry_set(&msrs[n++], MSR_LSTAR , env->lstar);
}
#endif
if (level == KVM_PUT_FULL_STATE) {
/*
* KVM is yet unable to synchronize TSC values of multiple VCPUs on
* writeback. Until this is fixed, we only write the offset to SMP
* guests after migration, desynchronizing the VCPUs, but avoiding
* huge jump-backs that would occur without any writeback at all.
*/
if (smp_cpus == 1 || env->tsc != 0) {
kvm_msr_entry_set(&msrs[n++], MSR_IA32_TSC, env->tsc);
}
kvm_msr_entry_set(&msrs[n++], MSR_KVM_SYSTEM_TIME, env->system_time_msr);
kvm_msr_entry_set(&msrs[n++], MSR_KVM_WALL_CLOCK, env->wall_clock_msr);
}
#ifdef KVM_CAP_MCE
if (env->mcg_cap) {
if (level == KVM_PUT_RESET_STATE)
kvm_msr_entry_set(&msrs[n++], MSR_MCG_STATUS, env->mcg_status);
else if (level == KVM_PUT_FULL_STATE) {
kvm_msr_entry_set(&msrs[n++], MSR_MCG_STATUS, env->mcg_status);
kvm_msr_entry_set(&msrs[n++], MSR_MCG_CTL, env->mcg_ctl);
for (i = 0; i < (env->mcg_cap & 0xff); i++)
kvm_msr_entry_set(&msrs[n++], MSR_MC0_CTL + i, env->mce_banks[i]);
}
}
#endif
rc = kvm_set_msrs(env, msrs, n);
if (rc == -1)
perror("kvm_set_msrs FAILED");
if (level >= KVM_PUT_RESET_STATE) {
kvm_arch_load_mpstate(env);
kvm_load_lapic(env);
}
if (level == KVM_PUT_FULL_STATE) {
if (env->kvm_vcpu_update_vapic)
kvm_tpr_enable_vapic(env);
}
kvm_put_vcpu_events(env, level);
kvm_put_debugregs(env);
/* must be last */
kvm_guest_debug_workarounds(env);
}
